COX REGRESSION WITH ALTERNATIVE CONCEPTS OF WAITING TIME - THE NEW-ORLEANS YELLOW-FEVER EPIDEMIC OF 1853

Event data can often be analysed using different concepts of waiting t ime. Our application offers three choices: calendar-time, age, and dur ation of residence in New Orleans. We exploit the semi-parametric feat ures of Cox regression and estimate parallel specifications in which m ortality risk is treated as an arbitrary function of one of the three alternative time measures, while the remaining two enter the hazard pa rametrically. Comparisons of the parameter estimates with the correspo nding estimates of the baseline hazards form the crux of a simple spec ification checking procedure. In our formal treatment we rely on Aalen 's Multiplicative Intensity formulation and tackle complications such as left-truncation, functional form specification, and choice-based sa mpling. (C) 1997 by John Wiley & Sons, Ltd.